Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 372,146 indexed, measured the same four ways as everything else here.
Official Feature-Sliced Design (FSD) v2.1 skill for applying the methodology to frontend projects. Use when the task involves organizing project structure with FSD layers, deciding where code belongs, placing static assets (images, icons, fonts, PDFs), grouping closely related slices, defining public APIs and import…
★not rated 100▲
+3
changed 3d agoASocket: passSnyk: pass192 tokens
A Model Context Protocol (MCP) integration for Minecraft that enables AI assistants to interact with a Minecraft server. This integration allows AI models to observe and interact with the Minecraft world through a bot. Runs locally from the mcp-minecraft npm package.
★not rated 100 1y agoA
tokens not measured
originalMIT
Minimal Excalidraw workflow for stable output. Steps: start session first, route Mermaid/manual inputs correctly, use the default Ghibli style, write in small batches, and verify.
Query and publish to an OpenLore knowledge base over SSH using ordinary shell commands. Use when a task needs project documentation, runbooks, shared team knowledge, or a place to publish findings.
MCP server "debug-tia-mcp-server" as configured in heilingbrunner/tiaportal-mcp. Launched with E:\Labor\GitHub\tiaportal-mcp\src\TiaMcpServer\bin\Debug\net48\TiaMcpServer.exe.
★not rated 100▲
+3 8d agoA
tokens not measured
originalMIT
Web accessibility (a11y) skills for Claude Code: audit a site for WCAG 2.2 conformance, scan a page with the rule engine, run hands-on keyboard and screen-reader checks, fix violations, and catch regressions in CI.
Diagnose and safely resume Coordinate Agents Tasks after executable failure, non-zero exit, timeout, stale claim, processing message, or Implementer ERROR. Recovery is explicit and never an automatic retry loop.
Neural web search for source-first research, especially official docs, API references, pricing pages, product specs, company pages, and any task where low-noise results and direct text extraction matter. Use when you need precise, high-quality, non-SEO-biased web results or extracted page text/highlights. Prefer this…
Technical guidance for recognizing human actions in video without training a new machine-learning model or using an LLM. It describes a pipeline that samples video frames, estimates body poses, measures movement, and assigns labels with rules.
MCP server "victoriametrics" as configured in Smana/cloud-native-ref. Launched with /usr/local/bin/mcp-victoriametrics. Needs 2 environment variables to run.
★not rated 99▲
+2 todayA
tokens not measured
originalApache-2.0
Correlate near-in-time events across PR merges, deploys, monitoring (Sentry/NewRelic/Datadog/AppDynamics) and ticket trackers (Jira/Azure DevOps) into confidence-scored clusters that answer "which deploy caused this bug" without manual tab-switching.
Plan architecture improvements and refactoring for a codebase: scan for deepening opportunities (shallow modules, leaky seams, low-leverage interfaces), present candidates as a markdown report with before/after diagrams, interview the user through the chosen design, and decompose the outcome into devchain epics. Use…
A Japanese-language novel-writing workflow that separates planning from drafting and stores story facts in searchable local memory. It supports genres including fantasy, science fiction, mystery, and romance.
★not rated 99
changed 3d agoA89 tokens
originalMIT
A Chinese-language guide to preparing software projects for reliable work by coding agents. It covers project instructions, documentation, code checks, tests for agent output, prompts, and ways to coordinate multiple agents.
Modern Deno development knowledge: dependency management, npm and JSR packages, permissions, the built-in toolchain, migrating from Node/npm/yarn/pnpm/bun, Fresh, and Deno Deploy.
★not rated 99▲
+1 1mo agoA
tokens not measured
originalMIT
AI Adoption, two skills for working with your Claude history. token-doctor diagnoses where your Claude Code + Cowork spend goes (length distribution, marathon share, sub-agent fan-out, model mix, cache rebuilds, per-project health), writes a doctor-style terminal report, and optionally fans out parallel Haiku…
★not rated 99
changed 2d agoA
tokens not measured
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: